Update benchmark script for NPU #11932
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
sgwhat
approved these changes
Aug 27, 2024
cyita
reviewed
Aug 27, 2024
| torch_dtype='auto', attn_implementation="eager").eval() | ||
| tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True) | ||
| elif repo_id in LLAMA_IDS: | ||
| model = AutoModelForCausalLM.from_pretrained(model_path, load_in_low_bit=low_bit, trust_remote_code=True, | ||
| optimize_model=optimize_model, max_output_len=max_output_len, max_prompt_len=int(in_out_len[0]), transpose_value_cache=True, |
There was a problem hiding this comment.
Should we add torch_dtype=torch.float16 as suggested in our example?
There was a problem hiding this comment.
Should we add
torch_dtype=torch.float16as suggested in our example?
Have updated.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
Update all-in-one benchmark script, we could also use all-in-one benchmark npu models with fused decoderlayer optimization.
usage:
set
optimize_modelas True in config.yaml4. How to test?